Broad learning for optimal short-term traffic flow prediction

Di Liu, Wenwu Yu*, Simone Baldi

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

4 Citations (Scopus)

Abstract

In this work, we explore the use of a Broad Learning System (BLS) as a way to replace deep learning architectures for traffic flow prediction. BLS is shown to not only outperforms standard learning algorithms (Least absolute shrinkage and selection operator (LASSO), shallow and deep neural networks, stacked autoencoders) in terms of training time, but also in terms of testing accuracy.

Original languageEnglish
Title of host publicationAdvances in Neural Networks
Subtitle of host publicationProceedings 16th International Symposium on Neural Networks (ISNN 2019)
EditorsHuchuan Lu, Huajin Tang, Zhanshan Wang
Place of PublicationCham, Switzerland
PublisherSpringer
Pages232-239
ISBN (Electronic)978-3-030-22796-8
ISBN (Print)978-3-030-22795-1
DOIs
Publication statusPublished - 2019
Event16th International Symposium on Neural Networks, ISNN 2019 - Moscow, Russian Federation
Duration: 10 Jul 201912 Jul 2019

Publication series

NameLecture Notes in Computer Science (LNCS)
Volume11554
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th International Symposium on Neural Networks, ISNN 2019
Country/TerritoryRussian Federation
CityMoscow
Period10/07/1912/07/19

Keywords

  • Broad Learning System
  • Fast least-square methods
  • Flat network
  • Traffic flow prediction

Fingerprint

Dive into the research topics of 'Broad learning for optimal short-term traffic flow prediction'. Together they form a unique fingerprint.

Cite this